Multi-source information collaborative intelligent compaction monitoring system based on dynamic compensation

Abstract

The invention relates to a multi-source information collaborative intelligent compaction monitoring system based on dynamic compensation, which comprises a data acquisition module, a displacement acquisition module, a data processing module, a shear wave velocity acquisition module and a soil body compaction degree value prediction model construction module, an intelligent compaction index, a soil pressure peak value in a soil body and an acceleration peak-to-peak value in the soil body are extracted through a data processing module, soil body displacement data are obtained through a displacement obtaining module, coordinates of a bending element sensor are corrected through a shear wave velocity obtaining module according to the soil body displacement data, and then the shear wave velocity is calculated. And the compaction degree of the soil body is obtained through an on-site sand filling method experiment. A neural network model is constructed by taking a soil pressure peak value in a soil body, an acceleration peak-to-peak value in the soil body, transverse and vertical shear wave velocities, soil body displacement data and an intelligent compaction index as input, and accurate prediction of the compaction degree is realized. According to the method, the precision, the real-time performance and the applicability of compaction quality evaluation are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent road construction, and particularly to a multi-source information collaborative intelligent compaction monitoring system based on dynamic compensation. Background Art

[0002] In modern road construction, the compaction quality of soil is crucial for the stability and durability of pavement engineering. Traditional compaction quality evaluation methods mostly rely on on-site tests. These methods not only take a long time, but may also have local non-uniformity and human errors, and cannot reflect the state of the soil during the compaction process in real time and comprehensively. In recent years, with the rapid development of artificial intelligence technology and sensing technology, intelligent compaction quality detection methods have gradually become the mainstream. The intelligent compaction technology uses sensors installed on the roller to collect the vibration signals of the roller in real time, and combines with the GPS positioning system to realize the real-time monitoring of the rolling process and the continuous evaluation of the compaction quality. However, most of the current research mainly focuses on the research of the vibration signals of the roller, which is difficult to comprehensively reflect the compaction state of the soil, and there is a lack of an intelligent monitoring system that combines the physical properties inside the soil (such as soil acceleration, displacement, soil pressure, shear wave velocity, etc.) with the external measurement signals of the roller for comprehensive collaborative evaluation.

[0003] During the construction process, it is relatively simple to measure the soil pressure of the soil, and data can usually be directly obtained by burying soil pressure sensors. However, there is a key problem: as the compaction process progresses, the sensor will settle and displace together with the soil, resulting in a change in the actual depth position corresponding to the measured data. It is relatively difficult to directly measure the settlement of the soil at different depths, especially without damaging the soil structure, and it is difficult to achieve with traditional methods. In addition, the existing technology calculates the settlement amount outside the soil by loading multiple displacement sensors on the roller, and the monitoring accuracy of this method needs to be improved. When obtaining the shear wave velocity by the bending element method, it is difficult to accurately calculate the distance between the transmitting end and the receiving end, which poses higher requirements for higher-precision intelligent monitoring by combining the physical properties inside the soil with the compaction performance. Summary of the Invention

[0004] The purpose of the present invention is to provide a multi-source information collaborative intelligent compaction monitoring system based on dynamic compensation to solve the problems raised in the above background art.

[0005] To achieve the above object, the technical solution adopted by the present invention is as follows: In the first aspect of the present invention, there is provided a multi-source information collaborative intelligent compaction monitoring system based on dynamic compensation, and the system includes: Data acquisition module, the data acquisition module includes a composite sensor arranged inside the compacted soil mass and an intelligent compaction device installed on a vibratory roller. The composite sensor includes an earth pressure sensor, an acceleration sensor, and a bender element sensor. The composite sensor is divided into two categories: a transmitting-end sensor and a receiving-end sensor according to whether the bender element sensor is a transmitting end or a receiving end. The earth pressure sensor is used to measure the earth pressure signal during the compaction process, the acceleration sensor is used to measure the acceleration signal inside the soil mass during the compaction process, and the bender element sensor is used to measure the shear wave signal of the soil mass during the compaction process. The intelligent compaction device is used to collect the vibration wheel acceleration signal, roller parameters, and position information during the entire compaction process. Data processing module, the data processing module includes a filtering unit and an extraction unit. The data processing module is used to process the data collected by the composite sensor and the intelligent compaction device during the compaction process. The filtered vibration wheel acceleration signal, filtered earth pressure signal, and filtered acceleration signal inside the soil mass are obtained through the filtering unit. The intelligent compaction index, the peak earth pressure inside the soil mass, and the peak-to-peak value of the acceleration inside the soil mass are extracted respectively through the extraction unit. Displacement acquisition module, the displacement acquisition module is electrically connected to the data processing module and is used to perform an integration operation on the acceleration based on the filtered acceleration signal inside the soil mass to obtain the soil displacement data. Shear wave velocity acquisition module, which is used to obtain the soil shear wave velocity data, including the horizontal shear wave velocity and the vertical shear wave velocity, based on the shear wave signal collected by the bender element sensor and the soil displacement data obtained by the displacement acquisition module. Soil compaction degree value prediction model construction module, based on a neural network model, using the dynamic response characteristic values and the intelligent compaction index as the input of the neural network model, and the compaction degree value as the output of the neural network model. The neural network model is optimized using an intelligent optimization algorithm, and the soil compaction degree value prediction model is obtained through training. The dynamic response characteristic values include the peak earth pressure inside the soil mass, the peak-to-peak value of the acceleration inside the soil mass, the horizontal shear wave velocity, the vertical shear wave velocity, and the soil displacement data.

[0006] Further, the arrangement method of the composite sensor inside the compacted soil mass is as follows: Use an electric drill to drill a vertical hole in the soil of the loose paving layer of the on-site road compaction construction. After digging to the depth set by the test plan, place the composite sensor at the bottom of the pit and backfill. Ensure that the soil medium particles in contact with the composite sensor are fine and smooth during the burial. The Z-axis of the composite sensor is vertically upward, and the X-axis is parallel to the advancing direction of the roller. When arranged horizontally, the transmitting sensor and the receiving sensor are respectively arranged on the left and right sides of the compacted road, horizontally aligned, and both are buried at the same depth in the loose paving layer for measuring the lateral shear wave signal of the soil mass; the horizontal distance between the horizontally arranged transmitting sensor and the receiving sensor is determined according to the width of the vibrating wheel of the roller; When arranged vertically, the transmitting sensor and the receiving sensor are arranged vertically in the loose paving layer in the middle and / or at the edge of the compacted road. The transmitting sensor and the receiving sensor are respectively located on the surface and the bottom of the loose paving layer for measuring the vertical shear wave signal of the soil mass; Along the advancing direction of the lane, a set of composite sensors is arranged horizontally or vertically every △L meters in the soil body during the compaction construction. Each set of composite sensors consists of a transmitting sensor and a receiving sensor, and they are distributed at intervals horizontally and vertically to simultaneously collect the lateral and vertical shear wave signals of the soil mass.

[0007] Furthermore, obtain the compaction degree at the position where each set of composite sensors is located. Use the peak value of the soil pressure inside the soil mass, the peak-to-peak value of the acceleration inside the soil mass, the lateral shear wave velocity, the vertical shear wave velocity, the soil displacement data, the intelligent compaction index, and the corresponding compaction degree obtained after each compaction as training samples to train the neural network model.

[0008] Furthermore, the drilling diameter is 5 - 10 cm, and the thickness of the loose paving layer is 20 - 30 cm.

[0009] Furthermore, the processing process of the filtering unit is as follows: Taking the signal peak value as the center point, take a 4-second signal segment before and after the center point respectively. Use the Hamming window to perform digital filtering on the total 8-second signal segment taken.

[0010] Furthermore, the process of performing an integration operation on the acceleration to obtain the soil displacement data is as follows: Perform a zeroing operation on the filtered acceleration signal inside the soil mass with the average value of the data in the first 2 seconds of the signal as the benchmark; define the moments when the acceleration signal inside the soil mass after the zeroing operation first and last exceeds the threshold acceleration as the vibration start moment t1 and the vibration end moment t2 respectively, and the threshold acceleration is determined according to the average peak value of the acceleration signal inside the soil mass under the condition of no load; Integrate the acceleration signal inside the soil mass after the zeroing operation to obtain a velocity signal; keep the integrated velocity data for the velocity signal before t1 without correction, and perform a least squares fit on the velocity signal during the time from t2 to the end of the whole record to obtain a fitting straight line; Connect the point corresponding to the t1 moment on the velocity signal and the point corresponding to the t2 moment on the fitting straight line with a straight line as the trend line of the vibration stage, and subtract the trend line of the vibration stage from the velocity signal to obtain the corrected velocity signal; Perform time-domain integration on the corrected speed signal to obtain the soil displacement signal, and extract the steady-state value within the time range from t2 to the end of the entire record as the soil displacement after compaction.

[0011] Further, the process of obtaining the soil shear wave velocity data is as follows: Each composite sensor consists of three earth pressure sensors, three acceleration sensors, and one bending element sensor inside. The three earth pressure sensors and acceleration sensors are arranged in three directions respectively. The soil displacement data in three directions can be obtained respectively through the data of the acceleration sensors in the three directions. Record the initial burial positions of the transmitting-end sensor and the receiving-end sensor in the form of three-dimensional coordinates. After each composite sensor obtains the soil displacements in three directions, correct the three-dimensional coordinates of the composite sensor respectively with the soil displacements in the three directions. Then calculate the distance between the transmitting-end sensor and the receiving-end sensor in each group of composite sensors based on their corrected three-dimensional coordinates, and further calculate the shear wave velocity according to the distance.

[0012] In the second aspect of the present invention, an electronic device is also provided. The electronic device includes at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the system of the first aspect.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: Based on the earth pressure signal and the soil internal acceleration signal collected inside the soil, the system of the present invention constructs a non-linear mapping relationship by fusing multi-source data and combining soil characteristic parameters to achieve accurate prediction of the compaction degree. The soil compaction degree value prediction model of the present invention can adapt to the changes of different soil types and construction conditions, dynamically evaluate the compaction degree in real time, and feedback the result to the operator to guide the adjustment of the compaction parameters, so as to realize the intelligent monitoring and closed-loop control of the compaction process.

[0014] The present invention significantly improves the accuracy, real-time performance, and applicability of the compaction quality evaluation, and provides an efficient and reliable technical support for the construction quality control of projects such as roads and railways. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic structural diagram of the multi-source information collaborative intelligent compaction monitoring system based on dynamic compensation in the present invention; Figure 2 It is a schematic layout diagram of the composite sensor during the compaction process in the present invention; Figure 3 It is a schematic diagram of the displacement signal with a trend item in time-domain integration; Figure 4 Schematic diagram of segmented acceleration signals; Figure 5 Schematic diagram of displacement signals obtained by integrating acceleration signals. Specific implementation manners

[0016] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention, but it does not limit the protection scope of this application. The embodiments described below are only examples, and those skilled in the art can think of other obvious variations.

[0017] Embodiment 1: Please refer to Figure 1 As shown, the multi-source information collaborative intelligent compaction monitoring system 100 based on dynamic compensation in this embodiment includes: A data acquisition module 110, which includes a composite sensor arranged inside the compacted soil mass and an intelligent compaction device installed on a vibratory roller. The composite sensor includes an earth pressure sensor, an acceleration sensor, and a bender element sensor. The earth pressure sensor is used to measure the earth pressure signal of the soil mass during compaction, the acceleration sensor is used to measure the internal acceleration signal of the soil mass during compaction, the bender element sensor is used to measure the shear wave signal of the soil mass during the compaction process, and the intelligent compaction device is used to collect the acceleration signal of the vibration wheel, roller parameters, position information, etc. during the entire compaction process.

[0018] A data processing module 120, which includes a filtering unit and an extraction unit. The data processing module is used to process the data collected by the composite sensor and the intelligent compaction device during the compaction process. The filtered acceleration signal of the vibration wheel, the filtered earth pressure signal, and the filtered internal acceleration signal of the soil mass are obtained through the filtering unit, and the intelligent compaction index, the peak earth pressure inside the soil mass, and the peak-to-peak value of the acceleration inside the soil mass are respectively extracted through the extraction unit.

[0019] A displacement acquisition module 130, which is electrically connected to the data processing module 120 and is used to perform an integration operation on the acceleration based on the filtered internal acceleration signal of the soil mass to obtain the soil mass displacement data; A shear wave velocity acquisition module 140, which is electrically connected to the displacement acquisition module 130 and is used to obtain the soil mass shear wave velocity data, including the horizontal shear wave velocity and the vertical shear wave velocity, based on the shear wave signal collected by the bender element sensor and the soil mass displacement data obtained by the displacement acquisition module.

[0020] Soil compaction value prediction model construction module 150. During the on-site compaction process, the soil near the composite sensor is selected and the compaction degree is measured by the sand replacement method. Based on the neural network model, with the dynamic response characteristic values and intelligent compaction indexes as the inputs of the neural network model and the compaction degree value as the output of the neural network model, the intelligent optimization algorithm is used to optimize the neural network model, and the soil compaction value prediction model is obtained through training. The soil compaction value prediction model has a high-accuracy prediction effect; the dynamic response characteristic values include the peak earth pressure inside the soil, the peak-to-peak acceleration inside the soil, the horizontal shear wave velocity, the vertical shear wave velocity, and the soil displacement data.

[0021] Those skilled in the art can understand that, in the present invention, by arranging composite sensors (earth pressure sensors, acceleration sensors, and bending element sensors) inside the compacted soil and installing intelligent compaction equipment on the vibratory roller, the system can simultaneously collect the earth pressure signal of the soil, the acceleration signal inside the soil, the shear wave signal, as well as the acceleration signal of the vibratory wheel of the roller, the roller parameters, and the position information. The filtering unit in the data processing module can effectively remove the noise and interference in the collected signals, improve the purity of the signals, and the extraction unit can extract key information from the signals processed by the filtering unit, such as intelligent compaction indexes, the peak-to-peak acceleration inside the soil, and the peak earth pressure inside the soil, which facilitates subsequent analysis. The shear wave velocity acquisition module corrects the distance between the receiving-end sensor and the transmitting-end sensor using the soil displacement data, and simultaneously calculates the shear wave velocity in combination with the shear wave signal. This parameter can reflect the mechanical properties and compaction effect of the soil.

[0022] Embodiment 2: In this embodiment, the soil compaction value prediction model construction module is implemented by using a neural network model and introducing the dragonfly algorithm, which can make full use of the learning ability of the neural network and the optimization ability of the dragonfly algorithm to obtain a soil compaction value prediction model with high accuracy and improve the prediction accuracy of the model. The soil compaction value prediction model with high accuracy can provide scientific guidance for construction. According to the predicted compaction degree value, it can help construction personnel adjust the compaction parameters in time, such as the compaction times, vibration frequency, etc., to ensure that the soil compaction degree meets the design requirements. At the same time, this model also helps to improve the project quality and reduce quality problems caused by insufficient compaction or over-compaction.

[0023] The dragonfly algorithm is as follows: ; ; ; ; ;

[0024] In the formula, , , , , respectively represent the displacement distances generated in the behaviors of collision avoidance, pairing, aggregation, predation, and enemy avoidance of the i-th dragonfly individual; and respectively represent the positions of the i-th and j-th dragonfly individuals, Y represents the number of dragonflies adjacent to the i-th dragonfly individual, represents the location of the food, represents the location of the natural enemy, and α, b, c, d, e respectively represent the weights of the dragonfly group behavior, represents the inertia weight, t is the current iteration number, represents the update step size of the t-th generation population; That is, the step vector at the t-th iteration.

[0025] The neural network model and the introduction of the dragonfly algorithm specifically include the following steps: Initialize the neural network model. The neural network model includes an input layer, an output layer, and a hidden layer. The dynamic response eigenvalue and the intelligent compaction index are used as the input of the input layer, and the output layer outputs the predicted compaction degree value. The dynamic response eigenvalue includes the peak earth pressure inside the soil mass, the peak-to-peak acceleration inside the soil mass, the horizontal shear wave velocity, the vertical shear wave velocity, and the soil displacement data (soil displacement data in three directions); when a certain value is missing, it is filled with 0.

[0026] Select the initial value of the dragonfly population behavior weight, and determine the dragonfly population size N and the iteration number T; Arrange the weights w and thresholds θ of the neural network model in an orderly manner to form a row vector (w, θ), which is used as the position X of the dragonfly individual. Set the range of weights and thresholds, and randomly initialize the position of the dragonfly individual according to the range of weights and thresholds; Calculate the fitness value of the dragonfly individual and record the current optimal solution; Select the mean square error as the fitness function, and update the location of the food and the location of the natural enemy , and update the population behavior of the dragonfly according to the above formula of the dragonfly algorithm , , , , ; Update the dragonfly step vector , if the iteration number t>T, then retain the connection weights w and thresholds θ, otherwise t=t + 1, and return to calculate the fitness value of the dragonfly individual; Take the weights \(w\) and threshold \(\theta\) corresponding to the optimal solution as the initial connection weights and threshold of the neural network, and then use the training samples to train the neural network model to obtain a prediction model for the soil compaction degree value with high accuracy.

[0027] Example 3: Please refer to Figure 2 As shown, arrange composite sensors inside the compacted soil, which specifically includes the following steps: When burying composite sensors inside the soil, the arrangement methods of the receiving - end sensor and the transmitting - end sensor have a direct impact on the measurement results of the shear wave velocity. The loose - laid thickness of on - site road compaction construction is generally 20 - 30 cm. Take the loose - laid thickness of 30 cm as an example.

[0028] Use a small - diameter (5 - 10 cm) electric drill to drill vertically into the loose - laid soil. After digging to the specified depth set by the test plan, put the composite sensor into the bottom of the pit, and select small - particle soil for backfilling. The Z - axis of the composite sensor is vertically upward, and the X - axis is parallel to the advancing direction of the roller. When arranging horizontally, the transmitting - end sensor and the receiving - end sensor are respectively arranged on the left and right sides of the compacted road, aligned in the horizontal direction, for measuring the horizontal shear wave signal of the soil. Both are buried at the same depth (such as 10 cm), that is, 20 cm from the surface of the compacted layer. The distance (horizontal distance) between the transmitting - end sensor and the receiving - end sensor needs to be determined according to the width of the vibrating wheel of the roller.

[0029] When arranging vertically, arrange a set of composite sensors vertically at a certain position (in the middle or at the edge) of the road. A set of composite sensors consists of a transmitting - end sensor and a receiving - end sensor. The transmitting - end sensor and the receiving - end sensor are respectively located at the upper end (surface) and the lower end (such as 30 cm deep) of the loose - laid layer, and the vertical distance is the thickness of the loose - laid layer, for measuring the vertical shear wave signal of the soil. To ensure the accuracy of the data results, when burying, ensure that the soil medium particles in contact with the sensor are fine. Coarse particles (such as gravel) will cause uneven distribution of contact stress, and local point loads will make the sensor readings on the high side.

[0030] Example 4: In this example, filter the data collected by the composite sensors and intelligent compaction equipment during the compaction process. The specific process is as follows: The amount of original signal data collected during the test is huge, so selective processing is required. Take the signal peak as the center point, and take 4 - second - long signal segments before and after the center point respectively. Use a Hamming window to perform digital filtering on the total 8 - second signal segment taken. The signals include the vibrating - wheel acceleration signal, the soil pressure signal, and the soil - internal acceleration signal. After being processed by the filtering unit, the filtered vibrating - wheel acceleration signal, the filtered soil pressure signal, and the filtered soil - internal acceleration signal are respectively obtained.

[0031] This 8 - second data covers the entire compaction process and reduces the storage and calculation burdens.

[0032] Feature parameters are extracted from the filtered vibratory drum acceleration signal, the filtered in - soil acceleration signal, and the filtered soil pressure signal. Among them, the characteristic value extracted from the filtered vibratory drum acceleration signal is the intelligent compaction index CMV, the characteristic value extracted from the filtered in - soil acceleration signal is the peak - to - peak value of the acceleration inside the soil; the characteristic value extracted from the filtered soil pressure signal is the peak value of the soil pressure inside the soil.

[0033] Example 5: In this embodiment, the process of obtaining the soil displacement data by integrating the acceleration is as follows: S1. The filtered in - soil acceleration signal is zeroed with the average value of the first 2 - second data of the signal as the reference to eliminate the initial offset of the instrument; S2. The moments when the zeroed in - soil acceleration signal first and last exceed the threshold acceleration are defined as the vibration start time t1 and the vibration end time t2 respectively; as Figure 4 shown, t1 is about 1.2 s and t2 = 7 s.

[0034] The threshold acceleration can be determined according to experience as 0.15 m / s²; the threshold acceleration is determined based on the average peak value of the acceleration signal under no - load conditions. Exceeding this value represents the influence of an external load, that is, the roller acts on the position where the sensor is buried. In this embodiment, 0.15 m / s² is defined as the peak value under no - load, which is the threshold acceleration.

[0035] S3. The zeroed in - soil acceleration signal is integrated to obtain a velocity signal, and the velocity signal shows a non - linear trend due to baseline drift; S4. The velocity data after integration is maintained for the velocity signal before t1 without correction, and the least - squares method is used to fit the velocity signal from t2 to the end of the entire record to obtain a fitting straight line; S5. Finally, a straight line is drawn to connect the point corresponding to t1 on the velocity signal and the point corresponding to t2 on the fitting straight line. This straight line is used as the trend line of the vibration stage, and the trend line of the vibration stage is subtracted from the velocity signal obtained in step S3 to obtain a corrected velocity signal, eliminating baseline drift; S6. The corrected velocity signal is integrated in the time domain to obtain a soil displacement signal, and the steady - state value from t2 to the end of the entire record is extracted as the soil displacement after compaction. As Figure 5 shown, t2 = 7 s, and the displacement curve gradually becomes stable after t2. The value when the displacement does not change is used as the steady - state value, that is, the steady - state displacement.

[0036] The acceleration signal is integrated once to obtain the velocity signal, and then integrated twice to obtain the displacement signal. If the conventional double integration of acceleration is used to obtain the displacement signal, the error will be amplified due to the accumulation of DC components and noise during the integration process. At this time, the displacement signal contains a trend term, as Figure 3 shown.

[0037] Example 6: In this embodiment, the process of obtaining the soil shear wave velocity data is as follows: Each composite sensor is composed of three earth pressure sensors, three acceleration sensors and a bending element sensor inside. The three earth pressure sensors and acceleration sensors are arranged in the X, Y, and Z directions respectively. The soil displacement data in the three directions can be obtained respectively through the data of the acceleration sensors in the three directions; Record the initial burial positions of the transmitting end sensor and the receiving end sensor in the form of three-dimensional coordinates (X, Y, Z). After each composite sensor obtains the soil displacements in the three directions, correct the three-dimensional coordinates of the composite sensor with the soil displacements in the three directions respectively. Then, calculate the distance between the transmitting end sensor and the receiving end sensor based on their respective corrected three-dimensional coordinates within each group of composite sensors, and further calculate the shear wave velocity according to the distance.

[0038] In this embodiment, X is the coordinate in the advancing direction of the roller, Y is the coordinate perpendicular to the advancing direction of the roller, and Z is the depth, with the unit of meter. For example, when a group of composite sensors A and B are arranged horizontally, the coordinates of the initial burial positions are A(0, 0, 0.3) and B(0, 2.2, 0.3) respectively, where 2.2m is the horizontal distance between sensors A and B, which is determined according to the width of the vibrating wheel. Z is the burial depth, which is determined by the depth during burial, and the X of the starting point of the paving is 0.

[0039] When a group of composite sensors A and B are arranged vertically, the coordinates of the initial burial positions are A(0, 0, 0) and B(0, 0, 0.3) respectively, where X is the coordinate in the advancing direction of the roller, Y is the coordinate perpendicular to the advancing direction of the roller, and Z is the depth, with the unit of meter. Among them, 0.3m is the vertical distance between sensors A and B, which is determined according to the thickness of the loose-laid soil layer. The X and Y of the starting point of the paving are both 0.

[0040] A is the transmitting end sensor and B is the receiving end sensor. Calculate the distance between the transmitting end sensor and the receiving end sensor based on the coordinates of the transmitting end sensor and the receiving end sensor corrected by the soil displacements in the three directions at each compaction moment; The formula for calculating the distance between the transmitting end sensor and the receiving end sensor is as follows:

[0041]

[0042]

[0043]

[0044] Wherein, is the corrected coordinate of the receiving - end sensor B on the X - axis, is the corrected coordinate of the transmitting - end sensor A on the X - axis, is the corrected coordinate of the receiving - end sensor on the Y - axis, is the corrected coordinate of the transmitting - end sensor on the Y - axis, is the corrected coordinate of the receiving - end sensor on the Z - axis, is the corrected coordinate of the transmitting - end sensor on the Z - axis, and L is the distance between the transmitting - end sensor and the receiving - end sensor; is the coordinate difference between the receiving - end sensor and the transmitting - end sensor on the X - axis, is the coordinate difference between the receiving - end sensor and the transmitting - end sensor on the Y - axis, is the coordinate difference between the receiving - end sensor and the transmitting - end sensor on the Z - axis.

[0045] Identify the first arrival point of the shear wave (i.e., the moment when the signal first significantly deviates from the baseline) from the signal obtained by the receiving - end sensor. Through the time - domain comparison of the signals obtained by the transmitting - end sensor and the receiving - end sensor, directly read the time difference. Divide the distance between the transmitting - end sensor and the receiving - end sensor by the time difference to calculate the horizontal shear wave velocity and the vertical shear wave velocity of the soil mass.

[0046] In this embodiment, the soil displacement data in three directions are obtained through the data of the acceleration sensors in three directions. This soil displacement data has directionality. When performing coordinate correction, only the initial three - dimensional coordinate values need to be uniformly added with the corresponding soil displacement data.

[0047] In the second aspect of the present invention, an electronic device is further provided. The electronic device includes at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the system of the first aspect of the present invention.

[0048] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above - mentioned embodiments. What is described in the above - mentioned embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection required by the present invention is defined by the appended claims and their equivalents.

[0049] What is not described in the present invention is applicable to the prior art.

Claims

1. A multi-source information collaborative intelligent compaction monitoring system based on dynamic compensation, characterized in that The system includes: A data acquisition module, which includes a composite sensor arranged inside the compacted soil mass and an intelligent compaction device installed on a vibratory roller. The composite sensor includes an earth pressure sensor, an acceleration sensor, and a bender element sensor. The composite sensors are classified into two categories: transmitting end sensors and receiving end sensors according to whether the bender element sensor is the transmitting end or the receiving end. The earth pressure sensor is used to measure the earth pressure signal during compaction, the acceleration sensor is used to measure the acceleration signal inside the soil mass during compaction, and the bender element sensor is used to measure the shear wave signal of the soil mass during compaction. The intelligent compaction device is used to collect the acceleration signal of the vibrating wheel, the roller parameters, and the position information during the entire compaction process; A data processing module, which includes a filtering unit and an extraction unit. The data processing module is used to process the data collected by the composite sensor and the intelligent compaction device during compaction. The filtered acceleration signal of the vibrating wheel, the filtered earth pressure signal, and the filtered acceleration signal inside the soil mass are obtained through the filtering unit. The intelligent compaction index, the peak earth pressure inside the soil mass, and the peak-to-peak acceleration inside the soil mass are respectively extracted through the extraction unit; A displacement acquisition module, which is electrically connected to the data processing module and is used to perform an integration operation on the acceleration based on the filtered acceleration signal inside the soil mass to obtain the soil displacement data; A shear wave velocity acquisition module, which is used to obtain the soil shear wave velocity data, including the horizontal shear wave velocity and the vertical shear wave velocity, based on the shear wave signal collected by the bender element sensor and the soil displacement data obtained by the displacement acquisition module; A soil compaction degree value prediction model construction module, which is based on a neural network model. The dynamic response characteristic values and the intelligent compaction index are used as the inputs of the neural network model, and the compaction degree value is used as the output of the neural network model. The neural network model is optimized by using an intelligent optimization algorithm, and the soil compaction degree value prediction model is obtained through training. The dynamic response characteristic values include the peak earth pressure inside the soil mass, the peak-to-peak acceleration inside the soil mass, the horizontal shear wave velocity, the vertical shear wave velocity, and the soil displacement data.

2. The multi-source information collaborative intelligent compaction monitoring system based on dynamic compensation according to claim 1, characterized in that The arrangement method of the composite sensor inside the compacted soil mass is as follows: For the loose paving layer of the on-site road compaction construction, a vertical hole is drilled into the soil using an electric drill. After digging to the depth set by the test plan, the composite sensor is placed at the bottom of the pit and backfilled. When burying, it is ensured that the soil medium particles in contact with the composite sensor are fine, the Z-axis of the composite sensor is vertically upward, and the X-axis is parallel to the advancing direction of the roller; When arranged horizontally, the transmitting end sensor and the receiving end sensor are respectively arranged on the left and right sides of the compacted road, horizontally aligned, and both are buried at the same depth in the loose paving layer for measuring the horizontal shear wave signal of the soil mass. The horizontal distance between the horizontally arranged transmitting end sensor and the receiving end sensor is determined according to the width of the roller vibrating wheel; When arranged vertically, the transmitting end sensor and the receiving end sensor are arranged vertically in the loose paving layer in the middle and / or at the edge of the compacted road. The transmitting end sensor and the receiving end sensor are respectively located on the surface and at the bottom of the loose paving layer, and are used to measure the vertical shear wave signal of the soil body. Along the advancing direction of the lane, a set of composite sensors is arranged horizontally or vertically every △L meters in the soil body during the compaction construction. Each set of composite sensors consists of a transmitting end sensor and a receiving end sensor, which are distributed at horizontal and vertical intervals, and the horizontal and vertical shear wave signals of the soil body are collected simultaneously.

3. The multi-source information collaborative intelligent compaction monitoring system based on dynamic compensation according to claim 2, characterized in that, Obtain the compaction degree of the position where each set of composite sensors is located, and use the peak value of the soil pressure inside the soil body, the peak-to-peak value of the acceleration inside the soil body, the horizontal shear wave velocity, the vertical shear wave velocity, the soil body displacement data, the intelligent compaction index and the corresponding compaction degree obtained after each compaction as training samples to train the neural network model.

4. The multi-source information collaborative intelligent compaction monitoring system based on dynamic compensation according to claim 2, wherein The diameter of the borehole is 5 - 10 cm, and the thickness of the loose paving layer is 20 - 30 cm.

5. The multi-source information collaborative intelligent compaction monitoring system based on dynamic compensation according to claim 1, characterized in that, The processing process of the filtering unit is as follows: Taking the signal peak as the center point, signal segments with a duration of 4 seconds are taken before and after the center point respectively, and the total 8-second signal segment taken is digitally filtered using a Hamming window.

6. The multi-source information collaborative intelligent compaction monitoring system based on dynamic compensation according to claim 1, wherein The process of performing an integration operation on the acceleration to obtain the soil body displacement data is as follows: Taking the average value of the data in the first 2 seconds of the filtered soil body internal acceleration signal as the reference for zeroing; defining the moments when the filtered soil body internal acceleration signal first and last exceeds the threshold acceleration as the vibration start moment t1 and the vibration end moment t2 respectively, and the threshold acceleration is determined according to the average peak value of the soil body internal acceleration signal under no load condition; Integrating the filtered soil body internal acceleration signal to obtain a velocity signal; keeping the integrated velocity data for the velocity signal before t1 without correction, and performing a least squares fit on the velocity signal from t2 to the end of the whole record to obtain a fitting straight line; Connecting the point corresponding to the t1 moment on the velocity signal and the point corresponding to the t2 moment on the fitting straight line with a straight line as the trend line of the vibration stage, and subtracting the trend line of the vibration stage from the velocity signal to obtain a corrected velocity signal; Performing a time-domain integration on the corrected velocity signal to obtain a soil body displacement signal, and extracting the steady-state value from t2 to the end of the whole record as the soil body displacement after compaction.

7. The multi-source information collaborative intelligent compaction monitoring system based on dynamic compensation according to claim 1, wherein The process of obtaining the soil body shear wave velocity data is as follows: Each composite sensor is composed of three soil pressure sensors, three acceleration sensors and a bending element sensor inside. The three soil pressure sensors and acceleration sensors are respectively arranged in three directions, and the soil body displacement data in three directions can be obtained respectively through the data of the acceleration sensors in three directions; Recording the initial burial positions of the transmitting end sensor and the receiving end sensor in the form of a three-dimensional coordinate. After each composite sensor obtains the soil body displacements in three directions, the three-dimensional coordinates of the composite sensor are corrected respectively with the soil body displacements in three directions; then calculating the distance between the transmitting end sensor and the receiving end sensor in each set of composite sensors based on their respective corrected three-dimensional coordinates, and further calculating the shear wave velocity according to the distance.

8. The multi-source information collaborative intelligent compaction monitoring system based on dynamic compensation according to claim 1, wherein, The intelligent optimization algorithm is the dragonfly algorithm.

Images